Yazar "Mohammadbagher Karimi" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim
    Öğe
    A cybersecurity method to detect SQL injection attacks using heuristic-driven feature selection and machine learning algorithms
    (Springer Nature, 26/12/2025) Bahman Arasteh Abbasabad; Mohammadbagher Karimi; Huseyin Kusetogullari; Farzad Kianı; Keyvan Arasteh
    SQL injection is a serious security risk that allows attackers to access application databases. SQL injection attacks can be identified using various methods, including machine learning algorithms. Finding the top-performing features in the training dataset is a combinatorial optimization problem known to be NP-complete. Finding the dataset's most effective and significant features is the goal of feature selection. This study aims to optimize the sensitivity, specificity, and accuracy of the SQL injection detection method. The first stage of the suggested method involved creating a unique training dataset with 13 characteristics. A binary form of the Whale Optimization Algorithm was suggested to find the most effective features in the dataset. An effective SQL injection detection system was developed by combining the whale algorithm as a feature selector with various machine learning techniques. The suggested SQL injection detector achieved 98.88% accuracy, 99.35% sensitivity, and a 98.83% F1-score using an artificial neural network and the whale optimizer. Using the proposed strategy to select about 31% of the features improved the performance of the attack detectors.
  • [ X ]
    Öğe
    A Feature Selection based Method for SQL Injection Detection Using Hybrid Machine Learning Algorithms
    (SAGE Publications- IOS PRESS, 8/12/2025) Mohammadbagher Karimi; Bahman Arasteh Abbasabad; Seyed Salar Sefati; Ibrahim Furkan Ince
    SQL injection (SQLi) is a serious security threat that allows attackers to access and manipulate databases through malicious input. Machine learning algorithms have shown strong potential for detecting SQL injection (SQLi) attacks. However, their performance depends heavily on the quality and relevance of the features used in training. Feature selection plays a key role in identifying the most effective, minimal set of features from the SQLi dataset. In this study, a hybrid SQLi detection method is proposed that combines feature selection with machine learning algorithms. A real-world dataset containing 13 features was first developed. Then, a hybrid Horse Herd Optimizer was developed and applied to select the most influential features before model training. Several machine learning classifiers were trained using the optimal feature set. The proposed method achieved high predictive performance, with 99.49% accuracy, 99.62% sensitivity, and 99.00% F1-score. These results were obtained using only about 45% of the original features. The reduction in feature size also improved the model's efficiency and training speed. The findings show that combining intelligent feature selection with machine learning significantly enhances SQLi detection. This approach is effective, scalable, and suitable for real-world security applications.